feat: update ai doc to cover model switching and turning ai off

Author: devvaannsh

docs/03-ai.md

@@ -27,6 +27,7 @@ Free users get a daily and monthly chat limit. Once you're past halfway on eithe
 - **[Plan, Auto-Edit, and Edit modes](#permission-modes)** let you decide how much freedom the AI has. Plan mode confirms before any change, Auto-Edit applies safe edits automatically, and Edit lets you approve each action.
 - **[Restore points and a visual undo timeline](#undo-and-restore)** mean every AI change is reversible. If you don't like what it did, roll back with one click.
 - **Live preview integration** — the AI can see your running app, take screenshots, click around, and verify its own work.
+- **[Choose the model](#choosing-a-model)** you want for each chat, even in the middle of a chat.
 - **[Bring your own provider](#settings)** — Claude from Anthropic (the default) gives the best results, or bring your own API key from any Claude Code CLI-compatible provider.
 - **Privacy-first onboarding** with a clear consent dialog and a video walkthrough.
 - **[Type while the AI is still working](#sending-messages)** — your next message gets queued.
@@ -39,6 +40,8 @@ AI requires the Claude Code CLI to be installed on your machine. If it's not ins
 
 Once installed, click **Set up Claude Code** to log in. Phoenix Code detects when the login is complete and opens the chat panel automatically.
 
+If your login expires later, the chat shows a **Claude Code is signed out or your login has expired** notice with a **Log in to Claude in Terminal** button. Click it, type `/login` in the terminal that opens, then send your message again.
+
 <VideoPlayer
   src="https://docs-images.phcode.dev/website/videos/claude-code-config.mp4"
 />
@@ -92,6 +95,19 @@ Click the **camera button** to take a screenshot and attach it. The dropdown let
 
 ![Camera screenshot dropdown](./images/pro/ai-screenshot-dropdown.png "Camera screenshot dropdown")
 
+## Choosing a Model
+
+The chat header shows which model is answering you. Hover over the panel and the model name appears on the left. Click it to pick a different one.
+
+<!-- TODO: PLUTO - add image here showing the model dropdown in the chat header -->
+
+The dropdown lists:
+
+- **Default**: lets Claude Code pick. The row shows which model that is right now, for example *Currently Opus*.
+- The models your provider offers, such as **Opus**, **Sonnet**, and **Haiku**.
+
+You can switch models in the middle of a chat. The new model takes over from your next message and keeps the conversation history.
+
 ## Permission Modes
 
 The AI has three permission levels that control how much it can do on its own. Click the **permission label** at the bottom of the panel to cycle between them.
@@ -159,6 +175,16 @@ Phoenix Code uses the Claude Code CLI under the hood, so it works with any provi
 - **z.ai GLM** — tested working as a drop-in alternative. Use z.ai's Anthropic-compatible endpoint as the base URL.
 - **Other Anthropic-API-compatible providers** — add the provider's base URL and API key in the dialog above.
 
+## Turning AI Off
+
+If you don't want AI in your editor, you can switch it off completely. Go to `View > Enable AI` and unselect it. Phoenix Code asks you to confirm, and the change takes effect after you restart the app.
+
+You can also do this from the AI settings dialog, with the **Enable AI features** checkbox.
+
+This turns off everything: the AI tab in the sidebar and the chat panel. To get it back, go to `View > Enable AI` again.
+
+> This is a user controlled preference. For schools and workplaces, please refer to [AI Control For School And Work](/docs/control-ai).
+
 ## Keyboard Shortcuts
 
 | Action | Shortcut |